© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 65915
    Prev
    Next
    INDEX
    Explanations

    foreign language characters

    np_acts-logits-general · gemini-2.5-flash-lite

    capturing specific parts or structured data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ₕ
    0.54
     admiss
    0.51
    悹
    0.51
     공부
    0.47
     encour
    0.47
     ambivalent
    0.47
     nisid
    0.47
     diagn
    0.47
     すご
    0.47
     karst
    0.47
    POSITIVE LOGITS
    aled
    0.46
    kost
    0.45
    pro
    0.45
    ιά
    0.45
    dí
    0.44
    哪
    0.44
    vi
    0.42
    gri
    0.42
    casts
    0.42
    出
    0.42
    Activations Density 0.001%

    No Known Activations